Project cost consultation management method and system

Abstract

The invention relates to the technical field of project cost consultation management, and discloses a project cost consultation management method and system, and the method comprises the steps: building a material price database which is dynamically updated in real time, obtaining market material price data from the Internet, and updating the material price database; adding the material price database into the data warehouse set, executing a cluster cache strategy, and optimizing the data warehouse set by using cache; executing a load balancing strategy on the server network of the transmission data warehouse set; acquiring data features of the cost project, executing an intelligent matching strategy, and acquiring an optimal cost model of the cost project; calculating the cost of the cost project by using the optimal cost model; if the cost is higher than the cost threshold, executing a budget project adjustment strategy, and adjusting budget distribution of sub-projects of the cost project; and executing the block chain recording strategy, and storing the operation record in the log record. And the reliability and accuracy of project cost management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of project cost consulting management, and specifically provides a project cost consulting management method and system. Background Art

[0002] Project cost management is a core component to ensure that projects are executed according to budget and achieve expected economic benefits. Its main goal is to reasonably predict and control various costs of the project, ensure the effective use of resources, and achieve optimal cost management throughout the project life cycle. Precise cost management can help the project team promptly identify potential cost overrun risks, take corresponding budget adjustment measures in a timely manner, and avoid unnecessary capital waste. In addition, good cost management can also improve the transparency and traceability of the project, provide real-time data support for decision-makers, optimize capital allocation, and ensure the successful completion of the project.

[0003] The existing project cost management solutions generally have the following problems: First, the update of material prices is slow and difficult to cope with market fluctuations, resulting in budget estimates often lagging behind and being unable to adjust costs in a timely manner; Second, most of the existing database management systems rely on a single-server architecture. As the amount of data increases, the system processing capacity and response speed decrease significantly, resulting in performance bottlenecks, especially prone to crashes or delays when facing concurrent requests; In addition, budget adjustments mostly rely on manual intervention, lacking real-time and accuracy. Budget deviations may only be discovered during the project progress, bringing difficulties to later management; Finally, the traditional log recording method lacks transparency, is prone to the risk of data tampering, and lacks effective auditing and tracking mechanisms, reducing the credibility of the system. Therefore, how to achieve real-time update, accurate prediction, intelligent adjustment, and data security in project management has become an urgent problem to be solved.

[0004] This solution proposes a project cost consulting management method and system to solve the problems mentioned in the background art. Summary of the Invention

[0005] The present invention provides a project cost consulting management method and system, which promotes the solution of the problems mentioned in the above background art.

[0006] In a first aspect, the present application provides a project cost consulting management method, adopting the following technical solution: A project cost consulting management method includes: S1. Establish a real-time and dynamically updated material price database, obtain market material price data on the Internet, and update the material price database; S2. Incorporate the material price database into the data warehouse for concentration, execute a cluster caching strategy, and use caching to optimize the data warehouse set; S3. Execute a load balancing strategy for the server network of the transmission data warehouse set to optimize the total server load; S4. Obtain historical project data from the data warehouse set, and use machine learning algorithms to train the historical project data to obtain all cost models; Obtain the data characteristics of this cost project, execute an intelligent matching strategy to obtain the optimal cost model for this cost project; Apply the optimal cost model to calculate the cost of this cost project; S5. Set a cost threshold; Compare the cost of this cost project with the cost threshold; If the cost is higher than the cost threshold, execute a budget project adjustment strategy to adjust the budget allocation of the sub-projects of this cost project; S6. Use a log recording system operation record; Execute a blockchain recording strategy to save the operation records in the log record.

[0007] By establishing a real-time dynamically updated material price database and integrating it with the data warehouse, the timeliness and accuracy of material prices are ensured. This makes budget adjustments more accurate and avoids cost overruns caused by lagging or inaccurate price information. By using a cluster caching strategy, the access speed and storage efficiency of the data warehouse are optimized. The application of the load balancing strategy ensures the stability of the system server, avoids performance bottleneck problems caused by the overload of a single node, and enables the system to still operate stably under high load. When using machine learning algorithms to train cost models from historical project data, the rules in the historical data can be extracted and used as a basis for predicting the cost of this project. This enables the system to not only provide a reliable budget based on historical data but also select the most suitable cost model through an intelligent matching strategy to ensure that the calculated cost is more in line with the actual project requirements. The setting of the cost threshold and the execution of the automatic budget adjustment strategy further ensure that the budget of the project can be optimized in real-time dynamically and avoid budget out-of-control caused by cost overruns. Finally, by recording each operation through blockchain technology, the immutability and transparency of system operations are ensured, providing data traceability, thereby enhancing the trust and security of the system.

[0008] Preferably, adding the material price database to the data warehouse set, executing a cluster caching strategy, and using caching to optimize the data warehouse set includes: Build a data warehouse cluster based on the Hadpoop ecosystem, specifically: Obtain the database used for project cost, divide the records in the database into n data blocks on average, where each data block contains D data records; Format the i-th data block D i Into the form of key-value pairs f(Di ) = {(K i , V i )}, where f(D i ) represents the mapping function that converts the data block D i into key-value pairs, and (K i , V i ) represent the keyword of the data block and the numerical value corresponding to the keyword respectively; Store the data block in the form of key-value pairs in the map task; For any keyword K j in the map task, perform a weighted average on all numerical values whose keyword is equal to K j where n is the number of numerical values whose keyword is equal to K ; j ; Set the number-of-times threshold; Obtain the query times of each keyword in the map task, compare the query times with the number-of-times threshold, and if the query times are greater than or equal to the number-of-times threshold, store the key-value pairs corresponding to the query times in the cache; Obtain the keyword entered by the user, denoted as the target keyword; Search for the target keyword in the cache; When the target keyword is found in the cache, return the numerical value corresponding to the target keyword in the cache; When the target keyword is not found in the cache, search for the target keyword in the database.

[0009] By building a data warehouse cluster based on the Hadoop ecosystem, the efficiency of large-scale data processing and storage has been significantly improved. The operations of evenly distributing data and converting it into key-value pairs enable each data block to be independently processed and analyzed, thus avoiding frequent access to the entire database and enhancing the system's processing capacity and data processing efficiency. The operation of performing a weighted average on each keyword enables the system to retain the accuracy of the data when processing large-scale data and to intelligently optimize the access to data blocks. By setting the query times threshold and the cache mechanism, the system can effectively reduce the performance waste caused by repeated queries, ensure that frequently used data can be quickly accessed, thereby reducing the response time and latency and enhancing the user experience. When the system queries the target keyword from the cache, it can directly return the corresponding numerical value, avoiding frequent access to the database, and when there is no data in the cache, the system will query through the database. This flexible data access method enables the system to dynamically adjust according to requirements in the face of different scenarios, thereby improving the system's processing efficiency and stability.

[0010] Preferably, implementing a load balancing strategy for the server network of the transmission data warehouse set to optimize the total server load includes: For any node in the server network, calculate the load of the node where are the CPU usage rate on node i, the memory usage ratio on node i, the disk I / O usage ratio on node i, and the network bandwidth usage ratio on node i respectively; ω1, ω2, ω3, ω4 are weight coefficients, indicating the relative contributions of various resources to the node load; Obtain the task set T of node i i ={T j |x ij =1}, where x ij =1 means that task T j is assigned to node i, and x ij =0 means that task T j is not assigned to node i; Calculate the minimum total load of the server where m is the total number of nodes in the server network.

[0011] By calculating the load of each node in the server network and assigning weights to resources such as CPU, memory, disk I / O, and network bandwidth, the optimal configuration of system resources is ensured. The relative contributions of each resource can be dynamically adjusted to achieve precise control of the loads of different nodes. This calculation method not only helps to ensure that the resources of each node are not overloaded, but also can maximize the operation efficiency of the entire server network and avoid resource waste. Through the reasonable allocation of tasks, the system can achieve load balancing between different nodes, avoid the overload problem of a single node, and improve the availability and stability of the system. When calculating the minimum total load of the server, by optimizing the load of each node, it is ensured that the system can efficiently process a large number of tasks and avoid system crashes or response delays caused by resource overload. Generally speaking, this load balancing mechanism can ensure the stable operation of the server cluster under high concurrency, providing a strong guarantee for the efficient operation of the project cost system.

[0012] Preferably, obtaining historical project data from the data warehouse concentration and using machine learning algorithms to train the historical project data to obtain all cost models includes: Obtain the characteristics H of historical project data i ={h1, h2,..., h r}, where h i represents the i-th feature and r is the number of features; Use a regression model to establish a cost model and calculate the project cost of the i-th historical engineering project: y i =β0 + β1h1 + β2h2 +... + β r hr + ε, where β0 is the intercept term, β1, β2, …, β r , are the regression coefficients of each feature, and ε is the error term; Use Lasso regression for regularizing the model: where λ is the regularization parameter, is the predicted value of the model, and y i is the true value; The optimal regression coefficients calculated according to the regularized model are used as the parameters of the model for historical project data i, and a cost model for each historical project data is obtained.

[0013] By using the regression model and the regularization technique of Lasso regression, a project cost model is constructed, providing an accurate prediction model for historical project data. Regression analysis can help the system capture the relationship between various features and costs by fitting historical project data with corresponding costs, ensuring the accuracy of cost prediction. Lasso regression avoids the overfitting problem through regularization, improves the generalization ability of the model, and enables the system to maintain a high prediction accuracy when facing new project data. The regularization process reduces the influence of noise by constraining the regression coefficients, further improving the prediction ability of the model. The advantage of this method is that it can provide personalized cost predictions by adjusting model parameters according to the characteristics of different projects, thus greatly improving the accuracy and reliability of the budget and avoiding errors caused by feature differences between historical projects and current projects.

[0014] Preferably, the obtaining of the data features of the current cost project and the execution of the intelligent matching strategy to obtain the optimal cost model of the current cost project include: Obtain the data features of the current cost project H′ = {h′1, h′2, …, h′ r}; Calculate the similarity between the data features of the current cost project and the data of the i-th historical project Obtain the optimal cost model of the historical project data with the highest similarity as the optimal cost model of the current cost project.

[0015] By obtaining the data characteristics of this project and comparing them with the historical project data, the system can find the most suitable historical project model based on the similarity, so as to provide the optimal cost prediction for the current project. This intelligent matching method based on data similarity can ensure that the cost model better fits the actual needs of the current project, making the prediction results more accurate. This mechanism optimizes the budget prediction by precisely calculating the similarity between project characteristics and effectively avoids the errors caused by using irrelevant or inaccurate historical data models. By selecting the historical data model most similar to this cost project, the system can improve the budget accuracy and achieve automated cost calculation and optimization, greatly improving the efficiency of budget prediction.

[0016] Preferably, if the construction cost is higher than the cost threshold, execute the budget project adjustment strategy to adjust the budget allocation of the sub-projects of this construction project, including: Calculate the budget deviation ΔC of the sub-projects of this construction project i =C i -C′ i , where C i represents the current actual cost of the i-th sub-project, and C′ i represents the budgeted cost of the i-th sub-project; Calculate the budget adjustment factor of the i-th sub-project where σ c is the standard deviation of the budget prediction of sub-project i; Set the budget adjustment value C″ of the i-th sub-project i ; Calculate the objective function of the budget project adjustment strategy Define where C is the construction cost of this construction project.

[0017] By calculating the budget deviation of the sub-projects and combining the budget adjustment factor, a scientific budget adjustment mechanism is provided. This mechanism compares the actual cost and budgeted cost of each sub-project, monitors and corrects the budget deviation in real time, and ensures that the project can remain within the predetermined budget range during the process. By using the standard deviation to measure the prediction error of the sub-project budget, the system can accurately identify the sub-projects with large budget deviations and make timely adjustments based on this information. The calculation of the budget adjustment factor provides a quantitative correction method for the deviation, making the budget adjustment more refined and avoiding the risks that may be brought by simple and rough budget adjustment methods. Through this method, the project manager can make reasonable adjustment decisions based on real-time data and budget deviation information, so as to keep the project within the budget control range and prevent overspending.

[0018] Preferably, execute the blockchain record strategy to save the operation records in the log records, including: The blockchain consists of blocks. Denote the i-th block as B i =(e i , t i , p i , w i ), where e i , t i , p i , w i are the hash value of block B i , the timestamp of the block, the hash value of block B i-1 , and the operation record stored in the block respectively; e i =H(t i ||p i ||w i ||ζ i ), where H(·) is a hash function, || is a concatenation operation, and ζ i represents a random number used for proof of work; Denote the hash chain as H(B1||B2||B3||…B q ), where q is the number of blocks.

[0019] The blockchain technology provides an immutable storage solution for the system operation records. The use of the blockchain enables each operation record to form a complete chain, and each block contains key fields such as a timestamp, a hash value, and a reference to the previous block, thus ensuring the security and transparency of the data. Such structured operation records not only enhance the trustworthiness of the system but also provide a clear operation history for easy traceability and auditing. Through the hash chain structure of the blockchain, the system can ensure the integrity and anti-tampering of the operation records. Even if the data is attacked or maliciously modified by insiders, the data can be restored and traced through the blockchain technology. This method provides higher security for the system and effectively avoids the risk of data loss or leakage.

[0020] In a second aspect, the present application provides a system for a project cost consulting management method, adopting the following technical solution: A system for a project cost consulting management method includes: Data collection and update module: responsible for real-time monitoring of network resources and collecting the latest building material prices and other economic data; Cost model matching engine: built-in with multiple algorithms to quickly screen the optimal cost calculation rules according to the project characteristics; Early warning and control center: integrated with a deep learning framework to identify abnormal cost patterns; Collaboration platform interface: designed with a human-computer interaction environment for sharing materials; Mobile client interface: Supports both Android / iOS platforms to ensure instant feedback on job status.

[0021] The present invention has the following beneficial effects: 1. For this project cost consulting management method, by establishing a real-time updated material price database, it ensures flexible response of the project to material price fluctuations. The dynamic update of the database enables the system to obtain the latest price information in the market at any time, thus avoiding budget errors caused by lagging data. Combined with the cluster caching strategy, the access efficiency of the data warehouse has been greatly improved. In addition, the implementation of the load balancing strategy ensures that the system can efficiently process a large amount of data and requests, reasonably allocate tasks among different nodes, and avoid the problem of overloading a single node, thereby improving the stability of the system. By using machine learning algorithms to train historical project data, the system can extract key cost models and automatically match the most suitable model according to the characteristics of the project, making the project budget more accurate. Once the budget exceeds the limit, the system will promptly trigger an adjustment strategy to avoid the risk of overspending. By combining blockchain technology to record operation logs, it ensures the transparency of the system and the immutability of data, enhancing the security and reliability of the system.

[0022] 2. For this project cost consulting management method, by dividing database records into multiple data blocks, each data block storing specific records, it enables data to be processed in parallel on different nodes, avoiding the bottleneck problem of a single node. In addition, the data blocks are converted into key-value pairs and processed in combination with Map tasks, improving the data access speed and calculation efficiency. By processing the numerical values corresponding to keywords through the weighted average algorithm, the system can accurately calculate the average value of each keyword according to actual needs, ensuring the accuracy and practicality of data analysis. After introducing the query times threshold and caching strategy, the system can effectively reduce frequent access to the database and improve the query efficiency. When the query times of the target keyword reach the set threshold, the relevant data will be cached, reducing the burden on the database and improving the response speed. If the required data is not in the cache, the system will automatically query from the database, ensuring the flexibility and efficiency of data access.

[0023] 3. This project cost consulting management method can accurately calculate the node load by comprehensively considering the resource usage of each node, including CPU, memory, disk I / O, and network bandwidth, thus avoiding excessive resource consumption. By assigning weight coefficients to each resource, it ensures a reasonable distribution of node loads and prevents performance degradation caused by a single resource bottleneck. Through the management of the node task set, the system can flexibly allocate tasks among different nodes, ensuring an even distribution of tasks and thereby improving the overall processing efficiency. The implementation of load balancing not only enhances the stability of the system but also minimizes failures and response delays caused by resource overload. When calculating the minimum total load of the computing server, the system optimizes the load distribution among nodes, enabling each node to perform at its best and avoiding the waste of resources where some nodes are idle while others are overloaded.

[0024] 4. This project cost consulting management method provides an efficient cost prediction tool for the system through the regularization process of the regression model and Lasso regression. The regression model can establish an accurate cost model for each project by fitting the relationship between historical project data and actual costs, helping the system predict the costs of future projects. Lasso regression can reduce overfitting of the model and improve its generalization ability by introducing a regularization term, enabling the system to maintain a high prediction accuracy when facing new projects. The regularization process can effectively control the complexity of the model and avoid interference from noise on the prediction results.

[0025] This not only improves the accuracy of the budget but also provides a solid theoretical basis for subsequent budget adjustments.

[0026] 1. This project cost consulting management method can achieve intelligent cost model matching by calculating the similarity between the current project and historical project data. By comparing the characteristics of the current project with historical data, the system can find the most suitable historical project model based on the similarity and use this model for cost prediction. The introduction of similarity calculation makes the budget prediction not only rely on fixed formulas or models but be able to be flexibly adjusted to fit the actual characteristics of the project. This intelligent matching mechanism not only improves the accuracy of budget prediction but also provides higher adaptability for the system. When the system can automatically select the optimal historical model according to the characteristics of the project, the budget prediction results are more in line with the actual situation, avoiding errors in traditional cost prediction methods.

[0027] 2. This project cost consulting management method ensures that the project can dynamically adjust the budget during the execution process to cope with uncertain external changes by real-time monitoring the budget deviation of sub-projects. By comparing the actual cost and budgeted cost of each sub-project, the system can quickly identify budget deviations and take timely measures for correction. The standard deviation is used as the basis for the budget adjustment factor, making the adjustment more refined, avoiding simple and crude budget adjustment methods, and ensuring the control of the project budget within a reasonable range. The introduction of the budget adjustment factor further enhances the system's adaptability to budget fluctuations. When the budget deviation is large, the system can automatically adjust the budget allocation of sub-projects to ensure that the overall project budget does not exceed the limit.

[0028] 3. This project cost consulting management method records the system operation logs through blockchain technology, ensuring the security and transparency of data. Each block contains a timestamp, a hash value, and a reference to the previous block. This structure not only guarantees the integrity of the data chain but also makes the operation records immutable. Through the hash chain structure of the blockchain, the system can trace back to each operation in case of anomalies, ensuring the transparency and fairness of the operation records. The introduction of this technology not only enhances the system's trust but also strengthens data security, preventing the risk of data tampering or loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a schematic diagram of the method flow of the present invention.

[0030] Figure 2 It is a schematic diagram of the system module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0032] Example 1, referring to Figure 1 , a project cost consulting management method includes: S1. Establish a real-time and dynamically updated material price database, obtain market material price data on the Internet, and update the material price database; S2. Add the material price database to the data warehouse concentration, execute the cluster caching strategy, and use caching to optimize the data warehouse concentration; S3. Execute a load balancing strategy for the server network transmitting the data warehouse concentration to optimize the total server load; S4. Obtain historical project data from the data warehouse in a centralized manner, and use machine learning algorithms to train the historical project data to obtain all cost models; Obtain the data characteristics of this cost project, execute the intelligent matching strategy, and obtain the optimal cost model for this cost project; Apply the optimal cost model to calculate the cost of this cost project; S5. Set the cost threshold; Compare the cost of this cost project with the cost threshold; If the cost is higher than the cost threshold, execute the budget project adjustment strategy to adjust the budget allocation of the sub-projects of this cost project; S6. Use the log to record the operation records of the system; Execute the blockchain recording strategy to save the operation records in the log.

[0033] By real-time dynamically updating the material price database, the problem of budget deviation caused by lagging or unforeseeable fluctuations in material prices in traditional project management is effectively solved. By continuously obtaining market prices from the Internet and updating the database, the project budget can reflect market dynamics in real time, ensuring the accuracy and timeliness of the budget. Especially in the case of large fluctuations in material prices, timely updating of data can significantly reduce the budget error caused by lagging price information, enabling project managers to adjust the budget according to the actual market situation. In addition, the implementation of the cluster caching strategy and load balancing further optimizes the performance of the system. The structure of the data warehouse in a centralized manner enables the effective management of massive data, while the caching strategy reduces the frequent access to the backend database, significantly improving the system response speed. The load balancing strategy ensures the even distribution of computing and storage tasks among multiple server nodes, preventing the over-concentration of resources on a single node, thus ensuring the stability and efficiency of the system. Machine learning algorithms can generate accurate cost models through learning historical project data and automatically select the optimal budget model according to the characteristics of this project, further improving the accuracy of cost budgeting. In addition, recording the operation history through blockchain technology ensures the transparency of the system and the immutability of data, providing reliable auditing and security guarantees for the project.

[0034] Add the material price database to the data warehouse in a centralized manner, execute the cluster caching strategy, and use caching to optimize the data warehouse set, including: Build a data warehouse cluster based on the Hadpoop ecosystem, specifically: Obtain the database used for project cost, and evenly divide the records in the database into n data blocks, where each data block contains D data records; Format the i-th data block D i into the form of key-value pairs f(D i ) = {(K i,V i )}, where f(D i ) represents the mapping function that converts data block D i into key-value pairs, and (K i ,V i ) represent the keyword of the data block and the numerical value corresponding to the keyword, respectively; Store the data block in key-value pair form in the map task; For any keyword K in the map task j , perform weighted average on all numerical values whose keyword is equal to K j where n is the number of numerical values whose keyword is equal to K j j ; Set the threshold of the number of times; Obtain the query times of each keyword in the map task, compare the query times with the threshold of the number of times, and if the query times are greater than or equal to the threshold of the number of times, store the key-value pairs corresponding to the query times in the cache; Obtain the keyword input by the user and record it as the target keyword; Search for the target keyword in the cache; When the target keyword is found in the cache, return the numerical value corresponding to the target keyword in the cache; When the target keyword is not found in the cache, search for the target keyword in the database.

[0035] Build a data warehouse cluster using the Hadoop ecosystem, which greatly improves the system's ability to process large-scale data. By evenly dividing the data in the project cost database into multiple data blocks and converting them into key-value pairs, the system can make full use of the advantages of distributed computing to achieve parallel processing of data. This structure enables the system to quickly and efficiently query and calculate data even in the face of a large amount of historical data, avoiding the performance bottleneck caused by excessive data volume in traditional centralized databases. By performing weighted average on the keywords in the data blocks, the system can extract important information and further optimize the query performance. Introduce a caching strategy. When the query times reach the set threshold, the relevant key-value pairs will be stored in the cache, which enables subsequent queries to return results faster, thereby improving the system's response speed and reducing the access pressure on the backend database. For the keyword input by the user, the system first searches in the cache. If the cache hits, the result can be quickly returned, further reducing the database burden; if the cache misses, the system will turn to the database to search, ensuring that the query result can be quickly returned regardless of whether the cache hits or not. This multi-level data processing mechanism not only improves the efficiency of data query, but also optimizes the resource utilization of the system and enhances the overall performance. Especially in the face of a large number of concurrent requests, it can ensure that the system still runs efficiently and stably.

[0036] Execute a load balancing strategy for the server network of the transmission data warehouse set to optimize the total server load, including: For any node in the server network, calculate the load of the node Among them, are respectively the CPU usage rate on node i, the memory usage ratio on node i, the disk i / o usage ratio on node i, and the network bandwidth usage ratio on node i; ω1, ω2, ω3, ω4 are weight coefficients, indicating the relative contribution of each resource to the node load; Obtain the task set T of node i i ={T j |x ij =1}, where x ij =1 means that task T j is assigned to node i, and x ij =0 means that task T j is not assigned to node i; Calculate the minimum total load of the server Among them, m is the total number of nodes in the server network.

[0037] By calculating the load of server nodes and reasonably allocating tasks, the efficient operation of the entire server network is ensured. The calculation of node load not only considers the CPU usage rate, memory usage ratio, disk I / O usage ratio, and network bandwidth usage ratio, but also introduces weight coefficients to measure the relative contribution of each resource to the load. This comprehensive evaluation method makes the load calculation more comprehensive and accurate, and can avoid the performance of the entire system being affected by a single resource bottleneck. By evaluating the load of each node, the system can intelligently allocate server tasks reasonably, ensure the best configuration of computing resources, and avoid the system performance degradation caused by individual node overload. In addition, calculating the minimum total load of the server enables the system to optimize resource allocation, avoid the situation where some nodes are idle while others are overloaded, thereby maximizing the utilization efficiency of resources. By dynamically adjusting the server load, the system can flexibly respond to changes in the volume of user requests and improve the stability of the system under high load. This optimization mechanism is particularly important for large-scale and high-concurrency systems, and can effectively avoid system crashes caused by single-point failures or resource bottlenecks, ensuring the high availability and stability of the system.

[0038] Obtain historical project data from the data warehouse set, and use machine learning algorithms to train the historical project data to obtain all cost models, including: Obtain the features H of the historical project data i ={h1, h2, …, h r},where h iIt represents the i-th feature, and r is the number of features; A cost model is established using a regression model to calculate the project cost of the i-th historical engineering project: y i = β0 + β1h1 + β2h2 + … + β r h r + ε, where β0 is the intercept term, β1, β2, …, β r , are the regression coefficients of each feature, and ε is the error term; Lasso regression is used for regularizing the model: where λ is the regularization parameter, is the model prediction value, and y i is the true value; The optimal regression coefficients calculated according to the regularized model are used as the parameters of the model for historical project data i, and the cost models for each historical project data are obtained.

[0039] By using a regression model to establish a cost model and combining the regularization technique of Lasso regression, the accuracy of cost prediction is effectively improved. The regression model takes into account multiple features (such as project scale, material usage, labor cost, etc.) and calculates the regression coefficients of each feature based on historical data, thereby obtaining the cost prediction of the project. This model can not only reflect the relationships between various variables but also make dynamic adjustments according to the changing trends of the data to adapt to the characteristics of different projects. Lasso regression can effectively avoid overfitting of the model and improve the generalization ability of the model on new data by introducing a regularization term. This is particularly important for project cost prediction because the cost is affected by multiple factors, and traditional regression models are prone to a decrease in prediction accuracy due to excessive feature selection or data noise. Lasso regression limits the complexity of the model through a penalty term, automatically selects important features, simplifies the model structure, and at the same time ensures the accuracy of the prediction results. In addition, the optimal regression coefficients adjusted through regularization can be used as the parameters of the model for historical project data to ensure the applicability of the model in different projects. Finally, this process can provide a more accurate budget estimate for the project, help project managers better control costs, and effectively avoid risks brought by budget deviations.

[0040] Obtain the data features of this cost project, execute an intelligent matching strategy, and obtain the optimal cost model for this cost project, including: Obtain the data features of this cost project H′ = {h′1, h′2, …, h′ r}; Calculate the similarity between the data features of this cost project and the data of the i-th historical project Obtain the optimal cost model of the historical project data with the highest similarity as the optimal cost model for this cost project.

[0041] By calculating the similarity between the current cost project and historical project data, the most suitable cost model for the current project can be intelligently selected, thereby improving the accuracy of budget prediction. The cost of a project is affected by various factors, such as project scale, material usage, labor cost, etc., and the characteristics of different historical projects may be highly similar to those of the current project. By calculating the similarity, the system can screen out the model that best matches the characteristics of the current project from a large amount of historical data, so as to provide a more accurate budget prediction for the current project. This intelligent matching strategy can effectively avoid errors in manual model selection. Especially when facing new types of projects, it can make analogies through existing historical data and provide effective references. The system calculates the similarity to find the most suitable historical project data, making the budget model more accurate and meeting the actual needs. This not only improves the accuracy of the budget, but also reduces the uncertainty brought by human intervention, improving the efficiency and accuracy of decision-making. At the same time, this strategy makes the model more updated and adaptable, and can dynamically select the optimal prediction model according to the changing project characteristics, further enhancing the intelligent level and adaptability of the system.

[0042] If the cost is higher than the cost threshold, execute the budget project adjustment strategy to adjust the budget allocation of the sub-projects of the current cost project, including: Calculate the budget deviation ΔC of the sub-projects of the current cost project i =C i -C′ i where C i represents the current actual cost of the i-th sub-project, and C′ i represents the budgeted cost of the i-th sub-project; Calculate the budget adjustment factor of the i-th sub-project where σ c is the standard deviation of the budget prediction of sub-project i; Set the budget adjustment value C″ of the i-th sub-project i ; Calculate the objective function of the budget project adjustment strategy Limit where C is the cost of the current cost project.

[0043] By calculating the budget deviation of sub-projects and setting the budget adjustment factor, it helps project managers detect budget overrun problems in a timely manner and make effective adjustments. The calculation of budget deviation can reflect the spending situation of each sub-project in real time, compare it with the budget, and identify those sub-projects that exceed the budget. This mechanism helps project managers detect potential financial risks at an early stage and take corresponding measures to control them. The introduction of the budget adjustment factor makes the budget adjustment of each sub-project more scientific and reasonable. Setting the adjustment value according to the standard deviation of the budget forecast of the sub-project can effectively avoid unnecessary adjustments caused by excessive budget fluctuations and ensure that the budget fluctuates within a reasonable range. At the same time, the setting of the objective function and the application of the budget item adjustment strategy can dynamically adjust the budget allocation of sub-projects when the project budget exceeds the limit, ensuring that the total cost of the overall project does not exceed the preset cost threshold. This adjustment strategy not only improves the flexibility of budget management but also effectively reduces the risk of over-budget, providing guarantee for the smooth implementation of the project.

[0044] Execute the blockchain record strategy to save the operation records in the log records, including: The blockchain consists of blocks. Denote the i-th block as B i =(e i , t i , p i , w i ), where e i , t i , p i , w i are the hash value of block B i , the timestamp of the block, the hash value of block B i-1 and the operation records stored in the block respectively; e i =H(t i ||p i ||w i ||ζ i ), where H(·) is the hash function, || is the concatenation operation, and ζ i represents the random number used for the proof of work; Denote the hash chain as H(B1||B2||B3||…B q ), where q is the number of blocks.

[0045] By using blockchain technology to record operation logs, the security, transparency, and immutability of system data are ensured. The hash value and timestamp of each block ensure the order of records and data integrity, while operation records provide a detailed audit trail for project management. The application of blockchain technology enables each operation to be accurately recorded and forms an immutable data chain, preventing the risks of human tampering and data loss. This mechanism enhances the trust in the system and ensures the authenticity and transparency of project data. Due to the decentralized nature of blockchain, the process of data storage and update is not controlled by a single node, thus avoiding the risk of single-point failure. At the same time, the use of proof-of-work nonce increases the security of the system and prevents malicious tampering of operation records. Through blockchain technology, the recording of operation logs not only realizes real-time data sharing but also provides a reliable basis for subsequent audits and tracking, greatly improving the security and transparency of project management and safeguarding the interests of all parties involved in the project.

[0046] Embodiment 2. Refer to Figure 2 , a system for a construction cost consulting management method, comprising: Data collection and update module: responsible for real-time monitoring of network resources and collecting the latest building material prices and other economic data; Cost model matching engine: built-in with multiple algorithms to quickly screen the optimal cost calculation rules according to project characteristics; Early warning and regulation center: integrated with a deep learning framework to identify abnormal cost patterns; Collaboration platform interface: designed for a human-computer interaction environment for sharing materials; Mobile client interface: supports both Android / iOS platforms to ensure instant feedback on the job status.

[0047] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0048] The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art in this technical field, without departing from the technical principle of the present invention, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for engineering cost consulting management, characterized in that, Including: S1. Establish a material price database with real-time dynamic updates, obtain market material price data on the Internet, and update the material price database; S2. Incorporate the material price database into the data warehouse concentration, execute a cluster caching strategy, and use caching to optimize the data warehouse concentration; S3. Execute a load balancing strategy for the server network transmitting the data warehouse concentration to optimize the total server load; S4. Obtain historical project data from the data warehouse concentration, and use machine learning algorithms to train the historical project data to obtain all cost models; Obtain the data characteristics of this cost project, execute an intelligent matching strategy, and obtain the optimal cost model for this cost project; Apply the optimal cost model to calculate the cost of this cost project; S5. Set a cost threshold; Compare the cost of this cost project with the cost threshold; If the cost is higher than the cost threshold, execute a budget project adjustment strategy to adjust the budget allocation of the sub-projects of this cost project; S6. Use a log recording system to record the operation records; Execute a blockchain recording strategy to save the operation records in the log records.

2. The project cost consulting management method according to claim 1, wherein, The incorporation of the material price database into the data warehouse concentration, execution of the cluster caching strategy, and use of caching to optimize the data warehouse concentration include: Build a data warehouse cluster based on the Hadpoop ecosystem, specifically: Obtain the database used for project cost, divide the records in the database into n data blocks on average, where each data block contains D data records; Format the i-th data block D i into the form of key-value pairs f(D i ) = {(K i , V i )}, where f(D i ) represents the mapping function that converts the data block D i into key-value pairs, and (K i , V i ) represent the keyword of the data block and the value corresponding to the keyword, respectively; Store the data blocks in key-value pair form in the map task; For any keyword K in the map task j , average all the values whose keyword is equal to K j weightedly. Among them, n is the number of values whose keyword is equal to K j ; Set a frequency threshold; Obtain the query frequency of each keyword in the map task, compare the query frequency with the frequency threshold, and if the query frequency is greater than or equal to the frequency threshold, store the key-value pair corresponding to the query frequency in the cache; Obtain the keyword input by the user, denoted as the target keyword; Search for the target keyword in the cache; When the target keyword is found in the cache, return the value corresponding to the target keyword in the cache; When the target keyword is not found in the cache, search for the target keyword in the database.

3. The project cost consulting management method according to claim 1, wherein, The execution of the load balancing strategy for the server network transmitting the data warehouse concentration to optimize the total server load includes: For any node in the server network, calculate the load of the node where are the CPU usage rate on node i, the memory usage ratio on node i, the disk I / O usage ratio on node i, and the network bandwidth usage ratio on node i, respectively; ω1, ω2, ω3, ω4 are weight coefficients, indicating the relative contributions of various resources to the node load; Obtain the task set \(T\) of node \(i\). i =\(\{T\ j |x ij = 1\}\), where \(x ij = 1\) indicates that task \(T j is assigned to node \(i\), and \(x ij = 0\) indicates that task \(T j is not assigned to node \(i\); Minimum total load of the computing server Where m is the total number of nodes in the server network.

4. The project cost consulting management method according to claim 1, wherein The obtaining of historical project data from the data warehouse concentration and the use of machine learning algorithms to train the historical project data to obtain all cost models include: Obtain the feature H of historical project data i ={h1, h2, …, h r}, where h i represents the i-th feature, and r is the number of features; Use a regression model to establish a cost model and calculate the project cost of the i-th historical engineering project: y i = β0 + β1h1 + β2h2 + … + β r h r + ε, where β0 is the intercept term, β1, β2, …, β r , are the regression coefficients of each feature, and ε is the error term; Using Lasso regression for regularizing the model: where λ is the regularization parameter, ŷ is the predicted value of the model, and y i is the true value; Use the optimal regression coefficient calculated according to the regularization model as the parameter of the historical project data i model to obtain the cost model of each historical project data.

5. The engineering cost consulting management method according to claim 4, wherein The obtaining of the data characteristics of this cost project, execution of the intelligent matching strategy, and obtaining of the optimal cost model for this cost project include: Obtain the data features H' = {h1 ' , h'2, …, h r '} of this cost project; Calculate the similarity between the data features of the current cost project and the data of the i-th historical project Obtain the optimal cost model of the historical project data with the highest similarity as the optimal cost model for this cost project.

6. The project cost consulting management method according to claim 1, characterized in that The execution of the budget project adjustment strategy to adjust the budget allocation of the sub-projects of this cost project if the cost is higher than the cost threshold includes: Calculate the budget deviation ΔC of the sub - project in this cost project i = C i - C i ' , where C i represents the current actual cost of the i - th sub - project, and C i ' represents the budgeted cost of the i - th sub - project; Calculate the budget adjustment factor for the i-th sub-project where σ c is the standard deviation of the budget forecast for sub-project i; Set the budget adjustment value C for the i-th sub-item i ”; Objective function for calculating the adjustment strategy of budget items Define Among them, C is the construction cost of this construction project.

7. The project cost consulting management method according to claim 1, wherein The execution of the blockchain recording strategy to save the operation records in the log records includes: The blockchain consists of blocks. The i-th block is denoted as B i =(e i ,t i ,p i ,w i ), where e i ,t i ,p i ,w i are the hash value of block B i , the timestamp of the block, the hash value of block B i-1 and the operation records stored in the block, respectively; e i = H(t i || p i || w i || ζ i ), where H(·) is a hash function, || is a concatenation operation, and ζ i represents a random number used for proof of work; Represent the hash chain as H(B1||B2||B3||…B q ), where q is the number of blocks.

8. A system for implementing the project cost consulting management method described in claim 1, including: Data collection and update module: Responsible for real-time monitoring of network resources, collecting the latest building material prices and other economic data; Cost model matching engine: Built-in with multiple algorithms, quickly screening the optimal cost calculation rules according to project characteristics; Early warning and control center: Integrated with a deep learning framework to identify abnormal cost patterns; Collaboration platform interface: Designing a human-computer interaction environment for sharing materials; Mobile client interface: Supporting both Android / iOS platforms to ensure instant feedback on the operation status.

Images